{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/111","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":111,"pages_in_order":142,"rows_per_page":100,"rows":[11001,11100],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/110","next":"/task/language-modeling/papers/112","papers":[{"url":null,"slug":"reduce-reuse-recycle-improving-training","title":"Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation","date":"2022-11-01","arxiv_id":"2211.00683","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-is-different-large-pre-trained","title":"The future is different: Large pre-trained language models fail in prediction tasks","date":"2022-11-01","arxiv_id":"2211.00384","repositories_listed":0,"syntology":null},{"url":"/paper/varmae-pre-training-of-variational-masked","slug":"varmae-pre-training-of-variational-masked","title":"VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding","date":"2022-11-01","arxiv_id":"2211.00430","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-yet-effective-approach-to-finding","title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","date":"2022-10-31","arxiv_id":"2211.00609","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-sequences-by-learning-to-self","title":"Generating Sequences by Learning to Self-Correct","date":"2022-10-31","arxiv_id":"2211.00053","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-hybrid-autoregressive-transducer","title":"Modular Hybrid Autoregressive Transducer","date":"2022-10-31","arxiv_id":"2210.17049","repositories_listed":0,"syntology":null},{"url":null,"slug":"pneg-prompt-based-negative-response-1","title":"Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task","date":"2022-10-31","arxiv_id":"2210.17238","repositories_listed":0,"syntology":null},{"url":null,"slug":"tables-to-latex-structure-and-content","title":"Tables to LaTeX: structure and content extraction from scientific tables","date":"2022-10-31","arxiv_id":"2210.17246","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-decompose-hypothetical-question","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","date":"2022-10-30","arxiv_id":"2210.16865","repositories_listed":0,"syntology":null},{"url":null,"slug":"token2vec-a-joint-self-supervised-pre","title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","date":"2022-10-30","arxiv_id":"2210.16755","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-meets-ctc-new-formulation-of-end-to-end","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2022-10-29","arxiv_id":"2210.16663","repositories_listed":0,"syntology":null},{"url":null,"slug":"ntulm-enriching-social-media-text-1","title":"NTULM: Enriching Social Media Text Representations with Non-Textual Units","date":"2022-10-29","arxiv_id":"2210.16586","repositories_listed":0,"syntology":null},{"url":null,"slug":"dimbert-learning-vision-language-grounded","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","date":"2022-10-28","arxiv_id":"2210.16431","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-engineering-vs-bert-on-twitter-data","title":"Feature Engineering vs BERT on Twitter Data","date":"2022-10-28","arxiv_id":"2210.16168","repositories_listed":0,"syntology":null},{"url":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","repositories_listed":0,"syntology":null},{"url":null,"slug":"upainting-unified-text-to-image-diffusion","title":"UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance","date":"2022-10-28","arxiv_id":"2210.16031","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-representation-of-human-motion","title":"Learning Joint Representation of Human Motion and Language","date":"2022-10-27","arxiv_id":"2210.15187","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearest-neighbor-language-models-for","title":"Nearest Neighbor Language Models for Stylistic Controllable Generation","date":"2022-10-27","arxiv_id":"2210.15762","repositories_listed":0,"syntology":null},{"url":null,"slug":"san-a-robust-end-to-end-asr-model","title":"SAN: a robust end-to-end ASR model architecture","date":"2022-10-27","arxiv_id":"2210.15285","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-language-learning-from-raw","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","date":"2022-10-27","arxiv_id":"2210.15759","repositories_listed":0,"syntology":null},{"url":null,"slug":"seq2seq-sc-end-to-end-semantic-communication","title":"Seq2Seq-SC: End-to-End Semantic Communication Systems with Pre-trained Language Model","date":"2022-10-27","arxiv_id":"2210.15237","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-realistic-speech-overlaps-improves","title":"Simulating realistic speech overlaps improves multi-talker ASR","date":"2022-10-27","arxiv_id":"2210.15715","repositories_listed":0,"syntology":null},{"url":null,"slug":"bloom-library-multimodal-datasets-in-300","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","date":"2022-10-26","arxiv_id":"2210.14712","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-pre-training-paradigm-for","title":"Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design","date":"2022-10-26","arxiv_id":"2211.08406","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-mechanism-priming-effects-in-hindi-word","title":"Dual Mechanism Priming Effects in Hindi Word Order","date":"2022-10-25","arxiv_id":"2210.13938","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-better-intent-representations-for","title":"Learning Better Intent Representations for Financial Open Intent Classification","date":"2022-10-25","arxiv_id":"2210.14304","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-open-data-and-task-augmentation-to","title":"Leveraging Open Data and Task Augmentation to Automated Behavioral Coding of Psychotherapy Conversations in Low-Resource Scenarios","date":"2022-10-25","arxiv_id":"2210.14254","repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-enhanced-transformer-with-ctc","title":"Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition","date":"2022-10-25","arxiv_id":"2210.14725","repositories_listed":0,"syntology":null},{"url":null,"slug":"rich-knowledge-sources-bring-complex","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","date":"2022-10-25","arxiv_id":"2210.13701","repositories_listed":0,"syntology":null},{"url":null,"slug":"same-pre-training-loss-better-downstream","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","date":"2022-10-25","arxiv_id":"2210.14199","repositories_listed":0,"syntology":null},{"url":null,"slug":"fcm-forgetful-causal-masking-makes-causal","title":"Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models","date":"2022-10-24","arxiv_id":"2210.13432","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bert-based-deep-learning-approach-for","title":"A BERT-based Deep Learning Approach for Reputation Analysis in Social Media","date":"2022-10-23","arxiv_id":"2211.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-language-model-as-semantic","title":"Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification","date":"2022-10-23","arxiv_id":"2210.12763","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-language-models-understand-measurements","title":"Do Language Models Understand Measurements?","date":"2022-10-23","arxiv_id":"2210.12694","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-gate-knowledge-distillation-leverage","title":"Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model","date":"2022-10-22","arxiv_id":"2210.12427","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmpriors-pre-trained-language-models-as-task","title":"LMPriors: Pre-Trained Language Models as Task-Specific Priors","date":"2022-10-22","arxiv_id":"2210.12530","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-3-lm-probabilistically-permuted-prophet","title":"P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training","date":"2022-10-22","arxiv_id":"2210.12339","repositories_listed":0,"syntology":null},{"url":null,"slug":"pentatron-personalized-context-aware","title":"PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding","date":"2022-10-22","arxiv_id":"2210.12308","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-lstm-spoken-term-detection-using-wav2vec","title":"Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer","date":"2022-10-21","arxiv_id":"2210.11885","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-encoder-decoder-redundant-for-neural","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","date":"2022-10-21","arxiv_id":"2210.11807","repositories_listed":0,"syntology":null},{"url":null,"slug":"litevl-efficient-video-language-learning-with","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","date":"2022-10-21","arxiv_id":"2210.11929","repositories_listed":0,"syntology":null},{"url":null,"slug":"spabert-a-pretrained-language-model-from","title":"SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation","date":"2022-10-21","arxiv_id":"2210.12213","repositories_listed":0,"syntology":null},{"url":null,"slug":"separating-grains-from-the-chaff-using-data","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","date":"2022-10-19","arxiv_id":"2210.10692","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-turn-debate-doesn-t-help-humans-answer","title":"Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions","date":"2022-10-19","arxiv_id":"2210.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-magma-by-few-shot-learning-and","title":"Aligning MAGMA by Few-Shot Learning and Finetuning","date":"2022-10-18","arxiv_id":"2210.14161","repositories_listed":0,"syntology":null},{"url":null,"slug":"hidden-state-variability-of-pretrained","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","date":"2022-10-18","arxiv_id":"2210.10041","repositories_listed":0,"syntology":null},{"url":null,"slug":"systematicity-in-gpt-3-s-interpretation-of","title":"Systematicity in GPT-3's Interpretation of Novel English Noun Compounds","date":"2022-10-18","arxiv_id":"2210.09492","repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-attention-adapter-contexts-are-more","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","date":"2022-10-18","arxiv_id":"2211.01979","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-bert-do-it-controller-area-network","title":"CAN-BERT do it? Controller Area Network Intrusion Detection System based on BERT Language Model","date":"2022-10-17","arxiv_id":"2210.09439","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgram-improving-scene-graph-parsing-via","title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","date":"2022-10-17","arxiv_id":"2210.08675","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-aware-non-autoregressive-spell","title":"Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding","date":"2022-10-16","arxiv_id":"2210.08665","repositories_listed":0,"syntology":null},{"url":null,"slug":"aralegal-bert-a-pretrained-language-model-for","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","date":"2022-10-15","arxiv_id":"2210.08284","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-generation-models-can-cause-harm-so","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","date":"2022-10-14","arxiv_id":"2210.07700","repositories_listed":0,"syntology":null},{"url":null,"slug":"levoice-asr-systems-for-the-iscslp-2022","title":"LeVoice ASR Systems for the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge","date":"2022-10-14","arxiv_id":"2210.07749","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-preference-learning-for-storytelling","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07792","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-out-of-domain-language-model","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","date":"2022-10-13","arxiv_id":"2210.06725","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-zero-resource-speech-recognition","title":"Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models","date":"2022-10-13","arxiv_id":"2210.06936","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-expansion-using-contextual-clue","title":"Query Expansion Using Contextual Clue Sampling with Language Models","date":"2022-10-13","arxiv_id":"2210.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"spontaneous-emerging-preference-in-two-tower","title":"Spontaneous Emerging Preference in Two-tower Language Model","date":"2022-10-13","arxiv_id":"2210.07041","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-covid-that-wasn-t-counterfactual","title":"The COVID That Wasn't: Counterfactual Journalism Using GPT","date":"2022-10-13","arxiv_id":"2210.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-generation-improves-open-domain","title":"Context Generation Improves Open Domain Question Answering","date":"2022-10-12","arxiv_id":"2210.06349","repositories_listed":0,"syntology":null},{"url":null,"slug":"datscore-evaluating-translation-with-data","title":"DATScore: Evaluating Translation with Data Augmented Translations","date":"2022-10-12","arxiv_id":"2210.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-context-processing-for-context","title":"Decoupled Context Processing for Context Augmented Language Modeling","date":"2022-10-11","arxiv_id":"2210.05758","repositories_listed":0,"syntology":null},{"url":null,"slug":"like-a-bilingual-baby-the-advantage-of","title":"Like a bilingual baby: The advantage of visually grounding a bilingual language model","date":"2022-10-11","arxiv_id":"2210.05487","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-s-eye-grounded-language-model-reasoning","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","date":"2022-10-11","arxiv_id":"2210.05359","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-bert-has-an-accent-evaluating","title":"Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models","date":"2022-10-11","arxiv_id":"2210.05619","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmentation-for-t5-re-ranker-using","title":"Retrieval Augmentation for T5 Re-ranker using External Sources","date":"2022-10-11","arxiv_id":"2210.05145","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustify-transformers-with-robust-kernel","title":"Designing Robust Transformers using Robust Kernel Density Estimation","date":"2022-10-11","arxiv_id":"2210.05794","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-sense-induction-with-hierarchical","title":"Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization","date":"2022-10-11","arxiv_id":"2210.05422","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-clip-and-stylegan-through-latent","title":"Bridging CLIP and StyleGAN through Latent Alignment for Image Editing","date":"2022-10-10","arxiv_id":"2210.04506","repositories_listed":0,"syntology":null},{"url":"/paper/do-children-texts-hold-the-key-to-commonsense","slug":"do-children-texts-hold-the-key-to-commonsense","title":"Do Children Texts Hold The Key To Commonsense Knowledge?","date":"2022-10-10","arxiv_id":"2210.04530","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-key-information-modeling-to","title":"Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning","date":"2022-10-10","arxiv_id":"2210.04473","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-probabilistic-circuits-by-latent","title":"Scaling Up Probabilistic Circuits by Latent Variable Distillation","date":"2022-10-10","arxiv_id":"2210.04398","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-transformer-pre-training-with","title":"Better Pre-Training by Reducing Representation Confusion","date":"2022-10-09","arxiv_id":"2210.04246","repositories_listed":0,"syntology":null},{"url":null,"slug":"qascore-an-unsupervised-unreferenced-metric","title":"QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation","date":"2022-10-09","arxiv_id":"2210.04320","repositories_listed":0,"syntology":null},{"url":null,"slug":"alphatuning-quantization-aware-parameter","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","date":"2022-10-08","arxiv_id":"2210.03858","repositories_listed":0,"syntology":null},{"url":null,"slug":"novice-type-error-diagnosis-with-natural","title":"Novice Type Error Diagnosis with Natural Language Models","date":"2022-10-07","arxiv_id":"2210.03682","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-semantic-role-labeling-with","title":"Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph","date":"2022-10-06","arxiv_id":"2210.03037","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-large-scale-paraphrase-acquisition","title":"Improving Large-scale Paraphrase Acquisition and Generation","date":"2022-10-06","arxiv_id":"2210.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-compression-and-contrastive","title":"Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models","date":"2022-10-06","arxiv_id":"2210.03162","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-lstm-language-model-decentralized-quantum","title":"PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection","date":"2022-10-06","arxiv_id":"2210.03221","repositories_listed":0,"syntology":null},{"url":null,"slug":"honest-students-from-untrusted-teachers","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","date":"2022-10-05","arxiv_id":"2210.02498","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-vulnerability-reports-through","title":"Enriching Vulnerability Reports Through Automated and Augmented Description Summarization","date":"2022-10-03","arxiv_id":"2210.01260","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-boundaries-of-meaning-a-case-study-in","title":"The boundaries of meaning: a case study in neural machine translation","date":"2022-10-02","arxiv_id":"2210.00613","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-parameter-contributions-when","title":"A Closer Look at Parameter Contributions When Training Neural Language and Translation Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-model-for-distantly-supervised","title":"A Simple Model for Distantly Supervised Relation Extraction","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tip-attribute-aware-text-infilling-via-pre","title":"A-TIP: Attribute-aware Text Infilling via Pre-trained Language Model","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exploration-of-prompt-based-zero-shot-1","title":"An Exploration of Prompt-Based Zero-Shot Relation Extraction Method","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arguably-smm4h22-classification-of-health","title":"ARGUABLY@SMM4H’22: Classification of Health Related Tweets using Ensemble, Zero-Shot and Fine-Tuned Language Model","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-mutual-learning-for-multi-source","title":"Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-detection-of-borrowings-in-low","title":"Automatic Detection of Borrowings in Low-Resource Languages of the Caucasus: Andic branch","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-nominalization-of-clauses","title":"Automatic Nominalization of Clauses","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-data-diversity-enhance-learning","title":"Can Data Diversity Enhance Learning Generalization?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-train-a-language-model-inside-an-end","title":"Can We Train a Language Model Inside an End-to-End ASR Model? - Investigating Effective Implicit Language Modeling","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complx-smm4h22-in-domain-pretrained-language","title":"CompLx@SMM4H’22: In-domain pretrained language models for detection of adverse drug reaction mentions in English tweets","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-synthesis-and-iterative-refinement-for","title":"Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deciphering-and-characterizing-out-of","title":"Deciphering and Characterizing Out-of-Vocabulary Words for Morphologically Rich Languages","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-meta-learning-help-mbert-for-few-shot","title":"Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-event-temporal-relation","title":"Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kul-smm4h22-template-augmented-adaptive-pre","title":"KUL@SMM4H’22: Template Augmented Adaptive Pre-training for Tweet Classification","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"64e9c692577ff56bdd5c5a39fe606aeb1afa77d9b2fef47d562873c4200946d8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}